Commit Graph

509 Commits

Author SHA1 Message Date
Mark Backman
53d403af4b Remove the RTVIServerMessage logic from the RTVIProcessor 2025-02-27 12:50:43 -05:00
Mark Backman
26c68ccd7c Add a new generic server to client message and frame type 2025-02-26 18:59:06 -05:00
Aleix Conchillo Flaqué
daa52ff8df update CHANGELOG for 0.0.58 2025-02-26 11:29:04 -08:00
Mark Backman
a5f41e22f7 Merge pull request #1299 from pipecat-ai/mb/add-track-level-recording
Added on_track_audio_data callback to AudioBufferProcessor for track level recording
2025-02-26 13:49:36 -05:00
Mark Backman
530bb5233d example: Added a foundational example (34) for audio recording 2025-02-26 13:44:32 -05:00
Mark Backman
1ca2101e3a Added on_track_audio_data callback to AudioBufferProcessor for track level recording 2025-02-26 10:48:56 -05:00
Aleix Conchillo Flaqué
e80311c323 Merge pull request #1296 from pipecat-ai/aleix/google-always-send-text-with-audio
GoogleLLMService: always send text with audio
2025-02-26 07:47:56 -08:00
Mark Backman
1753cc99f4 PlayHTHttpTTSService now takes a separate protocol input 2025-02-26 08:01:54 -05:00
Aleix Conchillo Flaqué
bb89a036e5 google: always send text part when sending inline audio 2025-02-25 22:27:38 -08:00
Aleix Conchillo Flaqué
6722aae598 PipelineTask: force constructor keyword arguments 2025-02-25 18:58:47 -08:00
Aleix Conchillo Flaqué
66564392a6 Merge pull request #1293 from pipecat-ai/aleix/log-pipecat-version
log pipecat version on application startup
2025-02-25 18:57:52 -08:00
Aleix Conchillo Flaqué
f8f0578c3d log pipecat version on application startup 2025-02-25 18:55:45 -08:00
Aleix Conchillo Flaqué
9a50f33e36 AudioContextWordTTSService: wait for all requested audio 2025-02-25 15:35:47 -08:00
Aleix Conchillo Flaqué
4bd5e9c0a7 Merge pull request #1285 from pipecat-ai/aleix/handle-stop-task-gracefully
handle stop task gracefully
2025-02-25 11:25:38 -08:00
Mark Backman
92cc6d39f2 TTSService: Remove newlines before sending text to TTS service to generate 2025-02-25 13:37:25 -05:00
Mark Backman
36a729cbfe Set grok-2 as default model for GrokLLMSService 2025-02-25 10:00:45 -05:00
Aleix Conchillo Flaqué
68789dfcf0 frames: add new StopFrame 2025-02-24 21:34:23 -08:00
Aleix Conchillo Flaqué
6028f0f23a PipelineTask: pass observers in contructor parameter 2025-02-24 21:29:17 -08:00
Aleix Conchillo Flaqué
e9a0959e28 Merge pull request #1283 from pipecat-ai/aleix/check-dangling-tasks
PipelineTask: add check_dangling_tasks parameter
2025-02-24 21:26:32 -08:00
Aleix Conchillo Flaqué
07b9be5308 PipelineTask: add check_dangling_tasks parameter 2025-02-24 17:33:10 -08:00
Aleix Conchillo Flaqué
40c2452d6e google: updgrade OpenAILLMContext to GoogleLLMContext 2025-02-24 15:35:18 -08:00
Aleix Conchillo Flaqué
2110b79507 services(llm): add on_completion_timeout event 2025-02-24 14:55:36 -08:00
Aleix Conchillo Flaqué
fc544fa61c Merge pull request #1272 from pipecat-ai/aleix/tts-websocket-interruptions
services: fix some TTS websocket service interruption handling
2025-02-24 14:54:41 -08:00
Mark Backman
d6f29a0f4b Update AnthropicLLMService to use claude-3-7-sonnet-20250219 by default 2025-02-24 14:32:00 -05:00
Aleix Conchillo Flaqué
5b637bd826 services: fix some TTS websocket service interruption handling 2025-02-24 08:37:22 -08:00
Aleix Conchillo Flaqué
b29ab8c608 observers: add LLMLogObserver and TranscriptionLogObserver 2025-02-21 15:15:16 -08:00
Aleix Conchillo Flaqué
12bce2e8c0 utils: add support for ellipses in match_endofsentence() 2025-02-21 15:05:50 -08:00
Aleix Conchillo Flaqué
41720b1a13 LLMUserContextAggregator: don't reset timer with interim transcription
It turns out that in some cases we only get interim transcriptions (e.g. someone
is speaking very very softly or someone is talking in the background). In those
cases we don't want to interrupt the bot because there's really nothing to
interrupt the bot for.

We originally thought we should interrupt the bot right at the time we got an
interim frame, but this is causing too many false positives. It's actually
better to simply wait for a real transcription before interrupting (in case VAD
didn't interrupt).
2025-02-21 09:05:56 -08:00
Aleix Conchillo Flaqué
3ef4245166 Merge pull request #1265 from pipecat-ai/aleix/transport-remove-audio-out-is-live 2025-02-21 06:51:09 -08:00
Filipi Fuchter
7c7b4c52af Fixed an issue where EndTaskFrame was not triggering on_client_disconnected or closing the WebSocket in FastAPI. 2025-02-21 09:11:58 -03:00
Aleix Conchillo Flaqué
01f083b7fc transports: remove TransportParams.audio_out_is_live 2025-02-20 23:33:06 -08:00
Vaibhav159
9c5fe5c85e fixing deepgram mismatch 2025-02-21 09:32:40 +05:30
Aleix Conchillo Flaqué
d04c4b36f3 AssistantContextAggregator: append aggregation and tools in the same turn 2025-02-20 17:29:43 -08:00
Aleix Conchillo Flaqué
69e6f3fdb7 rime: pass aiohttp session to constructor 2025-02-20 07:36:24 -08:00
Aleix Conchillo Flaqué
6809254963 tts: fix metrics and TTSStoppedFrame frame in HTTP services
Fixes #1247
2025-02-20 07:36:21 -08:00
Aleix Conchillo Flaqué
d9a67164f6 Merge pull request #1251 from pipecat-ai/aleix/fish-tts-service-push-stop-frame
FishAudioTTSService should push TTSStoppedFrame
2025-02-20 07:32:05 -08:00
Aleix Conchillo Flaqué
98259af54e update CHANGELOG 2025-02-19 22:05:48 -08:00
Aleix Conchillo Flaqué
6e3f96aa83 fish: automatically send TTSStoppedFrame after timeout 2025-02-19 21:41:18 -08:00
Filipi Fuchter
7e7926059c Fixed an issue that start_callback was not invoked for some LLM services. 2025-02-19 18:04:20 -03:00
Aleix Conchillo Flaqué
83f1a8830d daily: add room_url property 2025-02-19 09:29:53 -08:00
Aleix Conchillo Flaqué
1b0bcebef6 deepgram: use the new nova-3 model as default 2025-02-18 17:51:54 -08:00
Aleix Conchillo Flaqué
4edda718ed deepgram: add ability to provide custom addons 2025-02-18 17:45:41 -08:00
Aleix Conchillo Flaqué
50b6cc8135 network: added exponential_backoff_time() function 2025-02-18 17:42:43 -08:00
Aleix Conchillo Flaqué
c926063d74 deepgram: handle error event and reconnect 2025-02-18 09:52:18 -08:00
Aleix Conchillo Flaqué
90b9dce710 STTMuteFilter: ignore audio frames so no transcriptions are generated 2025-02-17 19:59:05 -08:00
Aleix Conchillo Flaqué
01c06c5cac update CHANGELOG for 0.0.57 2025-02-14 18:47:33 -08:00
Aleix Conchillo Flaqué
f6912c0f9a utils: don't consider colon an end of sentence 2025-02-14 18:47:33 -08:00
Aleix Conchillo Flaqué
633a4d4c58 FalImageGenService: load image async to not block the event loop 2025-02-14 18:47:33 -08:00
Aleix Conchillo Flaqué
b3a575c7c7 Merge pull request #1212 from Vaibhav159/vl_fix_incorrect_has_regular_messages_check
fixing google llm service error
2025-02-14 13:16:37 -08:00
Aleix Conchillo Flaqué
aeadb40c3f CartesiaTTSService: use AudioContextWordTTSService
By supporting multiple audio requests we fix an issue that was causing audio
overlapping.
2025-02-14 11:55:54 -08:00